SlideShare ist ein Scribd-Unternehmen logo
1 von 18
Downloaden Sie, um offline zu lesen
An exact mapping between the Variational
Renormalization Group and Deep Learning
Kai-Wen Zhao, kv
Physics, National Taiwan University
kelispinor@gmail.com
December 1, 2016
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 1 / 18
Outline
Overview
Renormalization Group
Physical world with various length scales
Symmetry and Scale Invariance
Restricted Boltzman Machine
Generative, Energy-based Model, Unsupervised Learning Algorithm
Richard Feynman: What I Cannot Create, I Do Not Understand.
Mapping
Unsupervised Deep Learning Implements the Kadanoff Real Space
Variational Renormalization Group
HRG
λ [{hj }] = HRBM
λ [{hj }]
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 2 / 18
Overview of Variational RG
Statistical Physics
An ensemble of N spins {vi }, take value ±1, i is position index in some
lattice. Boltzman distribution and partition function
P({vi }) =
e−H({vi })
Z
, where Z = Trvi e−H({vi })
=
v1,v2,...=±1
e−H({vi })
Typically, Hamiltonian depends on a set of couplings {Ks}
H[{vi }] = −
i
Ki vi −
ij
Kij vi vj −
ijk
Kijkvi vj vk + ...
Free energy of spin system
F = − log Z = − log(Trvi e−H({vi })
)
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 3 / 18
Overview of Variational RG
Overview of Variational Renormalization Group
Idea behind RG: To finde a new coarsed-grained description of spin
system, where one has integrated out short distance fluctuations.
N Physical spins: {vi }, couplings {K}
M Coarse-grained spins: {hj }, couplings { ˜K}, where M < N
Renormalization transformation is often represented as a mapping
{K} → { ˜K}
Coarse-grained Hamiltonian
HRG
[{hj }] = −
i
˜Ki hi −
ij
˜Kij hi hj −
ijk
˜Kijkhi hj hk + ...
Now, we do not distinguish vi and {vi } if no ambiguity
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 4 / 18
Overview of Variational RG
Overview of Variational Renormalization Group
Variational RG scheme (Kadanoff)
Coarse graining procedure: Tλ(vi , hj ) couples auxiliary spins hj to physical
spins vi
Naturally, we marginalize over the physical spins
exp (−HRG
λ (hj )) = Trvi exp (Tλ(vi , hj ) − H(vi ))
The free energy of coarse grained system
Fh
λ = −log(Trhj
e−HRG
λ (hj )
)
Choose parameters λ to ensure long-distrance observables are invariant.
Minimize free energy difference
∆F = Fh
λ − Fv
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 5 / 18
Overview of Variational RG
Overview of Variational Renormalization Group
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 6 / 18
RBMs and Deep Neural Networks
Restricted Boltzman Machine
Binary data probability distribution P(vi ). Energy function
E(vi , hj ) =
ij
wij vi hj +
i
ci vi +
j
bj hj
where we denote parameters λ = {w, b, c}. Joint probability
pλ(vi , hj ) =
e−E(vi ,hj )
Z
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 7 / 18
RBMs and Deep Neural Networks
Restricted Boltzman Machine
Variational distribution of visible variables
pλ(vi ) =
hj
p(vi , hj ) = Trhj
pλ(vi , hj ) :=
e−HRBM
λ (vi )
Z
pλ(hj ) =
vi
p(vi , hj ) = Trvi pλ(vi , hj ) :=
e−HRBM
λ (hj )
Z
Kullback-Leibler divergence
DKL(P(vi )||pλ(vi )) =
vi
P(vi ) log
P(vi )
pλ(vi )
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 8 / 18
Exact Mapping VRG to DL
Mapping Variational RG to RBM
In RG scheme, the couplings between visible and hidden spins are encodes
by the operators T. Analogous role, in RBM, is played by joint energy
function.
T(vi , hj ) = −E(vi , hj ) + H(vi )
To derive equivalent statement from coarse-grained Hamiltonian
e−HRG
λ (hj )
Z
=
Trvi eTλ(vi ,hj )−H(vi )
Z
= Trvi
e−E(vi ,hj )
Z
= pλ(hj )
=
e−HRBM
λ (hj )
Z
Subsituting the right-hand side yields
HRG
λ [{hj }] = HRBM
λ [{hj }] (1)
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 9 / 18
Exact Mapping VRG to DL
Mapping Variational RG to RBM
The operator Tλ can be viewed as a variational approximation for
conditional probability
eT(vi ,hj )
= e−E(vi ,hj )+H(vi )
=
pλ(vi , hj )
pλ(vi )
eH(vi )−HRBM
λ (vi )
= pλ(hj |vi )eH(vi )−HRBM
λ (vi )
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 10 / 18
Examples
Examples: 2D Ising Model
Two dimensional nearest neighbor Ising model with ferromagnetic coupling
H({vi }) = −J
<ij>
vi vj
Phase transition occurs when J/(kBT) = 0.4352.
Experiment Setup
20,000 samples, 40x40 periodic lattice
RBM’s architecture 1600-400-100-25
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 11 / 18
Examples
Examples: 2D Ising Model
Figure: Top layer
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 12 / 18
Examples
Examples: 2D Ising Model
Figure: Middle layer
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 13 / 18
Examples
Examples: 2D Ising Model
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 14 / 18
Conclusion
Conclusion and Discussion
One-to-one mapping between RBM-based DNN and variational RG
Suggest learning implements RG-like scheme to extract important
features from data
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 15 / 18
Relate to us
Relate to us: Auto-Encoder and Convolutional AE
z is the codes extracted by machine
φ : X → Z ψ : Z → X
arg min ||X − (ψ ◦ φ)X||2
Figure: Scheme of Auto-Encoder
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 16 / 18
Relate to us
Relate to us: Auto-Encoder and Convolutional AE
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 17 / 18
Relate to us
Thanks
Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 18 / 18

Weitere ähnliche Inhalte

Was ist angesagt?

Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Sangwoo Mo
 
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...Deep Learning JP
 
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)MeetupDataScienceRoma
 
Representation formula for traffic flow estimation on a network
Representation formula for traffic flow estimation on a networkRepresentation formula for traffic flow estimation on a network
Representation formula for traffic flow estimation on a networkGuillaume Costeseque
 
Traffic flow modeling on road networks using Hamilton-Jacobi equations
Traffic flow modeling on road networks using Hamilton-Jacobi equationsTraffic flow modeling on road networks using Hamilton-Jacobi equations
Traffic flow modeling on road networks using Hamilton-Jacobi equationsGuillaume Costeseque
 
Context-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationContext-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationDmitrii Ignatov
 
MAP Estimation Introduction
MAP Estimation IntroductionMAP Estimation Introduction
MAP Estimation IntroductionYoshiyama Kazuki
 
Clustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningClustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningFrank Nielsen
 
Second order traffic flow models on networks
Second order traffic flow models on networksSecond order traffic flow models on networks
Second order traffic flow models on networksGuillaume Costeseque
 
Clustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryClustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryFrank Nielsen
 
Dominación y extensiones óptimas de operadores con rango esencial compacto en...
Dominación y extensiones óptimas de operadores con rango esencial compacto en...Dominación y extensiones óptimas de operadores con rango esencial compacto en...
Dominación y extensiones óptimas de operadores con rango esencial compacto en...esasancpe
 
Computing the Nucleon Spin from Lattice QCD
Computing the Nucleon Spin from Lattice QCDComputing the Nucleon Spin from Lattice QCD
Computing the Nucleon Spin from Lattice QCDChristos Kallidonis
 
A common fixed point theorem for six mappings in g banach space with weak-com...
A common fixed point theorem for six mappings in g banach space with weak-com...A common fixed point theorem for six mappings in g banach space with weak-com...
A common fixed point theorem for six mappings in g banach space with weak-com...Alexander Decker
 
Quantitative norm convergence of some ergodic averages
Quantitative norm convergence of some ergodic averagesQuantitative norm convergence of some ergodic averages
Quantitative norm convergence of some ergodic averagesVjekoslavKovac1
 
Imecs2012 pp440 445
Imecs2012 pp440 445Imecs2012 pp440 445
Imecs2012 pp440 445Rasha Orban
 
Approximation Algorithms for the Directed k-Tour and k-Stroll Problems
Approximation Algorithms for the Directed k-Tour and k-Stroll ProblemsApproximation Algorithms for the Directed k-Tour and k-Stroll Problems
Approximation Algorithms for the Directed k-Tour and k-Stroll ProblemsSunny Kr
 
[DL輪読会]近年のエネルギーベースモデルの進展
[DL輪読会]近年のエネルギーベースモデルの進展[DL輪読会]近年のエネルギーベースモデルの進展
[DL輪読会]近年のエネルギーベースモデルの進展Deep Learning JP
 

Was ist angesagt? (20)

Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)
 
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
 
Pclsp ntnu
Pclsp ntnuPclsp ntnu
Pclsp ntnu
 
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)
Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)
 
Representation formula for traffic flow estimation on a network
Representation formula for traffic flow estimation on a networkRepresentation formula for traffic flow estimation on a network
Representation formula for traffic flow estimation on a network
 
Traffic flow modeling on road networks using Hamilton-Jacobi equations
Traffic flow modeling on road networks using Hamilton-Jacobi equationsTraffic flow modeling on road networks using Hamilton-Jacobi equations
Traffic flow modeling on road networks using Hamilton-Jacobi equations
 
Context-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationContext-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix Factorisation
 
Ceske budevice
Ceske budeviceCeske budevice
Ceske budevice
 
MAP Estimation Introduction
MAP Estimation IntroductionMAP Estimation Introduction
MAP Estimation Introduction
 
Clustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningClustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learning
 
Wasserstein GAN
Wasserstein GANWasserstein GAN
Wasserstein GAN
 
Second order traffic flow models on networks
Second order traffic flow models on networksSecond order traffic flow models on networks
Second order traffic flow models on networks
 
Clustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryClustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometry
 
Dominación y extensiones óptimas de operadores con rango esencial compacto en...
Dominación y extensiones óptimas de operadores con rango esencial compacto en...Dominación y extensiones óptimas de operadores con rango esencial compacto en...
Dominación y extensiones óptimas de operadores con rango esencial compacto en...
 
Computing the Nucleon Spin from Lattice QCD
Computing the Nucleon Spin from Lattice QCDComputing the Nucleon Spin from Lattice QCD
Computing the Nucleon Spin from Lattice QCD
 
A common fixed point theorem for six mappings in g banach space with weak-com...
A common fixed point theorem for six mappings in g banach space with weak-com...A common fixed point theorem for six mappings in g banach space with weak-com...
A common fixed point theorem for six mappings in g banach space with weak-com...
 
Quantitative norm convergence of some ergodic averages
Quantitative norm convergence of some ergodic averagesQuantitative norm convergence of some ergodic averages
Quantitative norm convergence of some ergodic averages
 
Imecs2012 pp440 445
Imecs2012 pp440 445Imecs2012 pp440 445
Imecs2012 pp440 445
 
Approximation Algorithms for the Directed k-Tour and k-Stroll Problems
Approximation Algorithms for the Directed k-Tour and k-Stroll ProblemsApproximation Algorithms for the Directed k-Tour and k-Stroll Problems
Approximation Algorithms for the Directed k-Tour and k-Stroll Problems
 
[DL輪読会]近年のエネルギーベースモデルの進展
[DL輪読会]近年のエネルギーベースモデルの進展[DL輪読会]近年のエネルギーベースモデルの進展
[DL輪読会]近年のエネルギーベースモデルの進展
 

Andere mochten auch

Learning RBM(Restricted Boltzmann Machine in Practice)
Learning RBM(Restricted Boltzmann Machine in Practice)Learning RBM(Restricted Boltzmann Machine in Practice)
Learning RBM(Restricted Boltzmann Machine in Practice)Mad Scientists
 
Restricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theoryRestricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theorySeongwon Hwang
 
Logging : How much is too much? Network Security Monitoring Talk @ hasgeek
Logging : How much is too much? Network Security Monitoring Talk @ hasgeekLogging : How much is too much? Network Security Monitoring Talk @ hasgeek
Logging : How much is too much? Network Security Monitoring Talk @ hasgeekvivekrajan
 
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...Indraneel Pole
 
Brief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineBrief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineArunabha Saha
 
Ibm log differentiators for strategic network planning 2011 v6
Ibm log differentiators for strategic network planning 2011 v6Ibm log differentiators for strategic network planning 2011 v6
Ibm log differentiators for strategic network planning 2011 v6Artem Vinogradov
 
Machine Learning: An Introduction Fu Chang
Machine Learning: An Introduction Fu ChangMachine Learning: An Introduction Fu Chang
Machine Learning: An Introduction Fu Changbutest
 
LSTM 네트워크 이해하기
LSTM 네트워크 이해하기LSTM 네트워크 이해하기
LSTM 네트워크 이해하기Mad Scientists
 
First-passage percolation on random planar maps
First-passage percolation on random planar mapsFirst-passage percolation on random planar maps
First-passage percolation on random planar mapsTimothy Budd
 
mtc All Hands 8/15 Werte
mtc All Hands 8/15 Wertemtc All Hands 8/15 Werte
mtc All Hands 8/15 WerteArne Krueger
 
20131011 - Los Gatos - Netflix - Big Data Design Patterns
20131011 - Los Gatos - Netflix - Big Data Design Patterns20131011 - Los Gatos - Netflix - Big Data Design Patterns
20131011 - Los Gatos - Netflix - Big Data Design PatternsAllen Day, PhD
 
Artificial intelligence 2015: Quo Vadis?
Artificial intelligence 2015: Quo Vadis?Artificial intelligence 2015: Quo Vadis?
Artificial intelligence 2015: Quo Vadis?Sergey Shelpuk
 
Machine Learning and Logging for Monitoring Microservices
Machine Learning and Logging for Monitoring Microservices Machine Learning and Logging for Monitoring Microservices
Machine Learning and Logging for Monitoring Microservices Daniel Berman
 

Andere mochten auch (20)

Learning RBM(Restricted Boltzmann Machine in Practice)
Learning RBM(Restricted Boltzmann Machine in Practice)Learning RBM(Restricted Boltzmann Machine in Practice)
Learning RBM(Restricted Boltzmann Machine in Practice)
 
Restricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theoryRestricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theory
 
Logging : How much is too much? Network Security Monitoring Talk @ hasgeek
Logging : How much is too much? Network Security Monitoring Talk @ hasgeekLogging : How much is too much? Network Security Monitoring Talk @ hasgeek
Logging : How much is too much? Network Security Monitoring Talk @ hasgeek
 
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...
Restricted Boltzmann Machine - A comprehensive study with a focus on Deep Bel...
 
Brief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineBrief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann Machine
 
Ibm log differentiators for strategic network planning 2011 v6
Ibm log differentiators for strategic network planning 2011 v6Ibm log differentiators for strategic network planning 2011 v6
Ibm log differentiators for strategic network planning 2011 v6
 
Machine Learning: An Introduction Fu Chang
Machine Learning: An Introduction Fu ChangMachine Learning: An Introduction Fu Chang
Machine Learning: An Introduction Fu Chang
 
restrictedboltzmannmachines
restrictedboltzmannmachinesrestrictedboltzmannmachines
restrictedboltzmannmachines
 
LSTM 네트워크 이해하기
LSTM 네트워크 이해하기LSTM 네트워크 이해하기
LSTM 네트워크 이해하기
 
DNN and RBM
DNN and RBMDNN and RBM
DNN and RBM
 
Percolation Model and Controllability
Percolation Model and ControllabilityPercolation Model and Controllability
Percolation Model and Controllability
 
Logging in moodle
Logging in moodleLogging in moodle
Logging in moodle
 
Machine Learning at Scale
Machine Learning at ScaleMachine Learning at Scale
Machine Learning at Scale
 
First-passage percolation on random planar maps
First-passage percolation on random planar mapsFirst-passage percolation on random planar maps
First-passage percolation on random planar maps
 
mtc All Hands 8/15 Werte
mtc All Hands 8/15 Wertemtc All Hands 8/15 Werte
mtc All Hands 8/15 Werte
 
20131011 - Los Gatos - Netflix - Big Data Design Patterns
20131011 - Los Gatos - Netflix - Big Data Design Patterns20131011 - Los Gatos - Netflix - Big Data Design Patterns
20131011 - Los Gatos - Netflix - Big Data Design Patterns
 
Percolation
PercolationPercolation
Percolation
 
Elastic Search
Elastic SearchElastic Search
Elastic Search
 
Artificial intelligence 2015: Quo Vadis?
Artificial intelligence 2015: Quo Vadis?Artificial intelligence 2015: Quo Vadis?
Artificial intelligence 2015: Quo Vadis?
 
Machine Learning and Logging for Monitoring Microservices
Machine Learning and Logging for Monitoring Microservices Machine Learning and Logging for Monitoring Microservices
Machine Learning and Logging for Monitoring Microservices
 

Ähnlich wie Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning

Prof. Rob Leigh (University of Illinois)
Prof. Rob Leigh (University of Illinois)Prof. Rob Leigh (University of Illinois)
Prof. Rob Leigh (University of Illinois)Rene Kotze
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Valentin De Bortoli
 
Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningSungbin Lim
 
Linear response theory and TDDFT
Linear response theory and TDDFT Linear response theory and TDDFT
Linear response theory and TDDFT Claudio Attaccalite
 
Persistence of power-law correlations in nonequilibrium steady states of gapp...
Persistence of power-law correlations in nonequilibrium steady states of gapp...Persistence of power-law correlations in nonequilibrium steady states of gapp...
Persistence of power-law correlations in nonequilibrium steady states of gapp...Jarrett Lancaster
 
Structured Regularization for conditional Gaussian graphical model
Structured Regularization for conditional Gaussian graphical modelStructured Regularization for conditional Gaussian graphical model
Structured Regularization for conditional Gaussian graphical modelLaboratoire Statistique et génome
 
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...Hiroyuki KASAI
 
(DL hacks輪読) Variational Inference with Rényi Divergence
(DL hacks輪読) Variational Inference with Rényi Divergence(DL hacks輪読) Variational Inference with Rényi Divergence
(DL hacks輪読) Variational Inference with Rényi DivergenceMasahiro Suzuki
 
Value Function Geometry and Gradient TD
Value Function Geometry and Gradient TDValue Function Geometry and Gradient TD
Value Function Geometry and Gradient TDAshwin Rao
 
Alexei Starobinsky - Inflation: the present status
Alexei Starobinsky - Inflation: the present statusAlexei Starobinsky - Inflation: the present status
Alexei Starobinsky - Inflation: the present statusSEENET-MTP
 
Gradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation GraphsGradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation GraphsYoonho Lee
 
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modeling
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modelingHamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modeling
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modelingGuillaume Costeseque
 
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...Guillaume Costeseque
 
Some recent developments in the traffic flow variational formulation
Some recent developments in the traffic flow variational formulationSome recent developments in the traffic flow variational formulation
Some recent developments in the traffic flow variational formulationGuillaume Costeseque
 
From Atomistic to Coarse Grain Systems - Procedures & Methods
From Atomistic to Coarse Grain Systems - Procedures & MethodsFrom Atomistic to Coarse Grain Systems - Procedures & Methods
From Atomistic to Coarse Grain Systems - Procedures & MethodsFrank Roemer
 

Ähnlich wie Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning (20)

g-lecture.pptx
g-lecture.pptxg-lecture.pptx
g-lecture.pptx
 
Prof. Rob Leigh (University of Illinois)
Prof. Rob Leigh (University of Illinois)Prof. Rob Leigh (University of Illinois)
Prof. Rob Leigh (University of Illinois)
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
Presentation
PresentationPresentation
Presentation
 
Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep Learning
 
Linear response theory and TDDFT
Linear response theory and TDDFT Linear response theory and TDDFT
Linear response theory and TDDFT
 
Persistence of power-law correlations in nonequilibrium steady states of gapp...
Persistence of power-law correlations in nonequilibrium steady states of gapp...Persistence of power-law correlations in nonequilibrium steady states of gapp...
Persistence of power-law correlations in nonequilibrium steady states of gapp...
 
Structured Regularization for conditional Gaussian graphical model
Structured Regularization for conditional Gaussian graphical modelStructured Regularization for conditional Gaussian graphical model
Structured Regularization for conditional Gaussian graphical model
 
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...
Riemannian stochastic variance reduced gradient on Grassmann manifold (ICCOPT...
 
(DL hacks輪読) Variational Inference with Rényi Divergence
(DL hacks輪読) Variational Inference with Rényi Divergence(DL hacks輪読) Variational Inference with Rényi Divergence
(DL hacks輪読) Variational Inference with Rényi Divergence
 
Value Function Geometry and Gradient TD
Value Function Geometry and Gradient TDValue Function Geometry and Gradient TD
Value Function Geometry and Gradient TD
 
Polynomial Matrix Decompositions
Polynomial Matrix DecompositionsPolynomial Matrix Decompositions
Polynomial Matrix Decompositions
 
the ABC of ABC
the ABC of ABCthe ABC of ABC
the ABC of ABC
 
Alexei Starobinsky - Inflation: the present status
Alexei Starobinsky - Inflation: the present statusAlexei Starobinsky - Inflation: the present status
Alexei Starobinsky - Inflation: the present status
 
Gradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation GraphsGradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation Graphs
 
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modeling
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modelingHamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modeling
Hamilton-Jacobi equations and Lax-Hopf formulae for traffic flow modeling
 
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...
Contribution à l'étude du trafic routier sur réseaux à l'aide des équations d...
 
BSE and TDDFT at work
BSE and TDDFT at workBSE and TDDFT at work
BSE and TDDFT at work
 
Some recent developments in the traffic flow variational formulation
Some recent developments in the traffic flow variational formulationSome recent developments in the traffic flow variational formulation
Some recent developments in the traffic flow variational formulation
 
From Atomistic to Coarse Grain Systems - Procedures & Methods
From Atomistic to Coarse Grain Systems - Procedures & MethodsFrom Atomistic to Coarse Grain Systems - Procedures & Methods
From Atomistic to Coarse Grain Systems - Procedures & Methods
 

Mehr von Kai-Wen Zhao

Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human labelKai-Wen Zhao
 
Deep Double Descent
Deep Double DescentDeep Double Descent
Deep Double DescentKai-Wen Zhao
 
Recent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionRecent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionKai-Wen Zhao
 
Learning to discover monte carlo algorithm on spin ice manifold
Learning to discover monte carlo algorithm on spin ice manifoldLearning to discover monte carlo algorithm on spin ice manifold
Learning to discover monte carlo algorithm on spin ice manifoldKai-Wen Zhao
 
Toward Disentanglement through Understand ELBO
Toward Disentanglement through Understand ELBOToward Disentanglement through Understand ELBO
Toward Disentanglement through Understand ELBOKai-Wen Zhao
 
Deep Reinforcement Learning: Q-Learning
Deep Reinforcement Learning: Q-LearningDeep Reinforcement Learning: Q-Learning
Deep Reinforcement Learning: Q-LearningKai-Wen Zhao
 
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...Kai-Wen Zhao
 
High Dimensional Data Visualization using t-SNE
High Dimensional Data Visualization using t-SNEHigh Dimensional Data Visualization using t-SNE
High Dimensional Data Visualization using t-SNEKai-Wen Zhao
 

Mehr von Kai-Wen Zhao (8)

Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
 
Deep Double Descent
Deep Double DescentDeep Double Descent
Deep Double Descent
 
Recent Object Detection Research & Person Detection
Recent Object Detection Research & Person DetectionRecent Object Detection Research & Person Detection
Recent Object Detection Research & Person Detection
 
Learning to discover monte carlo algorithm on spin ice manifold
Learning to discover monte carlo algorithm on spin ice manifoldLearning to discover monte carlo algorithm on spin ice manifold
Learning to discover monte carlo algorithm on spin ice manifold
 
Toward Disentanglement through Understand ELBO
Toward Disentanglement through Understand ELBOToward Disentanglement through Understand ELBO
Toward Disentanglement through Understand ELBO
 
Deep Reinforcement Learning: Q-Learning
Deep Reinforcement Learning: Q-LearningDeep Reinforcement Learning: Q-Learning
Deep Reinforcement Learning: Q-Learning
 
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...
NIPS paper review 2014: A Differential Equation for Modeling Nesterov’s Accel...
 
High Dimensional Data Visualization using t-SNE
High Dimensional Data Visualization using t-SNEHigh Dimensional Data Visualization using t-SNE
High Dimensional Data Visualization using t-SNE
 

Kürzlich hochgeladen

BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxolyaivanovalion
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxolyaivanovalion
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionfulawalesam
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...amitlee9823
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 

Kürzlich hochgeladen (20)

BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interaction
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 

Paper Review: An exact mapping between the Variational Renormalization Group and Deep Learning

  • 1. An exact mapping between the Variational Renormalization Group and Deep Learning Kai-Wen Zhao, kv Physics, National Taiwan University kelispinor@gmail.com December 1, 2016 Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 1 / 18
  • 2. Outline Overview Renormalization Group Physical world with various length scales Symmetry and Scale Invariance Restricted Boltzman Machine Generative, Energy-based Model, Unsupervised Learning Algorithm Richard Feynman: What I Cannot Create, I Do Not Understand. Mapping Unsupervised Deep Learning Implements the Kadanoff Real Space Variational Renormalization Group HRG λ [{hj }] = HRBM λ [{hj }] Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 2 / 18
  • 3. Overview of Variational RG Statistical Physics An ensemble of N spins {vi }, take value ±1, i is position index in some lattice. Boltzman distribution and partition function P({vi }) = e−H({vi }) Z , where Z = Trvi e−H({vi }) = v1,v2,...=±1 e−H({vi }) Typically, Hamiltonian depends on a set of couplings {Ks} H[{vi }] = − i Ki vi − ij Kij vi vj − ijk Kijkvi vj vk + ... Free energy of spin system F = − log Z = − log(Trvi e−H({vi }) ) Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 3 / 18
  • 4. Overview of Variational RG Overview of Variational Renormalization Group Idea behind RG: To finde a new coarsed-grained description of spin system, where one has integrated out short distance fluctuations. N Physical spins: {vi }, couplings {K} M Coarse-grained spins: {hj }, couplings { ˜K}, where M < N Renormalization transformation is often represented as a mapping {K} → { ˜K} Coarse-grained Hamiltonian HRG [{hj }] = − i ˜Ki hi − ij ˜Kij hi hj − ijk ˜Kijkhi hj hk + ... Now, we do not distinguish vi and {vi } if no ambiguity Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 4 / 18
  • 5. Overview of Variational RG Overview of Variational Renormalization Group Variational RG scheme (Kadanoff) Coarse graining procedure: Tλ(vi , hj ) couples auxiliary spins hj to physical spins vi Naturally, we marginalize over the physical spins exp (−HRG λ (hj )) = Trvi exp (Tλ(vi , hj ) − H(vi )) The free energy of coarse grained system Fh λ = −log(Trhj e−HRG λ (hj ) ) Choose parameters λ to ensure long-distrance observables are invariant. Minimize free energy difference ∆F = Fh λ − Fv Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 5 / 18
  • 6. Overview of Variational RG Overview of Variational Renormalization Group Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 6 / 18
  • 7. RBMs and Deep Neural Networks Restricted Boltzman Machine Binary data probability distribution P(vi ). Energy function E(vi , hj ) = ij wij vi hj + i ci vi + j bj hj where we denote parameters λ = {w, b, c}. Joint probability pλ(vi , hj ) = e−E(vi ,hj ) Z Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 7 / 18
  • 8. RBMs and Deep Neural Networks Restricted Boltzman Machine Variational distribution of visible variables pλ(vi ) = hj p(vi , hj ) = Trhj pλ(vi , hj ) := e−HRBM λ (vi ) Z pλ(hj ) = vi p(vi , hj ) = Trvi pλ(vi , hj ) := e−HRBM λ (hj ) Z Kullback-Leibler divergence DKL(P(vi )||pλ(vi )) = vi P(vi ) log P(vi ) pλ(vi ) Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 8 / 18
  • 9. Exact Mapping VRG to DL Mapping Variational RG to RBM In RG scheme, the couplings between visible and hidden spins are encodes by the operators T. Analogous role, in RBM, is played by joint energy function. T(vi , hj ) = −E(vi , hj ) + H(vi ) To derive equivalent statement from coarse-grained Hamiltonian e−HRG λ (hj ) Z = Trvi eTλ(vi ,hj )−H(vi ) Z = Trvi e−E(vi ,hj ) Z = pλ(hj ) = e−HRBM λ (hj ) Z Subsituting the right-hand side yields HRG λ [{hj }] = HRBM λ [{hj }] (1) Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 9 / 18
  • 10. Exact Mapping VRG to DL Mapping Variational RG to RBM The operator Tλ can be viewed as a variational approximation for conditional probability eT(vi ,hj ) = e−E(vi ,hj )+H(vi ) = pλ(vi , hj ) pλ(vi ) eH(vi )−HRBM λ (vi ) = pλ(hj |vi )eH(vi )−HRBM λ (vi ) Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 10 / 18
  • 11. Examples Examples: 2D Ising Model Two dimensional nearest neighbor Ising model with ferromagnetic coupling H({vi }) = −J <ij> vi vj Phase transition occurs when J/(kBT) = 0.4352. Experiment Setup 20,000 samples, 40x40 periodic lattice RBM’s architecture 1600-400-100-25 Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 11 / 18
  • 12. Examples Examples: 2D Ising Model Figure: Top layer Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 12 / 18
  • 13. Examples Examples: 2D Ising Model Figure: Middle layer Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 13 / 18
  • 14. Examples Examples: 2D Ising Model Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 14 / 18
  • 15. Conclusion Conclusion and Discussion One-to-one mapping between RBM-based DNN and variational RG Suggest learning implements RG-like scheme to extract important features from data Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 15 / 18
  • 16. Relate to us Relate to us: Auto-Encoder and Convolutional AE z is the codes extracted by machine φ : X → Z ψ : Z → X arg min ||X − (ψ ◦ φ)X||2 Figure: Scheme of Auto-Encoder Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 16 / 18
  • 17. Relate to us Relate to us: Auto-Encoder and Convolutional AE Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 17 / 18
  • 18. Relate to us Thanks Kai-Wen Zhao, kv (NTU-PHYS) Review December 1, 2016 18 / 18